Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "revision" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orman
    -0.16
    strict
    -0.15
    pon
    -0.15
    erna
    -0.14
    ume
    -0.14
     Electronics
    -0.14
    acus
    -0.14
    cu
    -0.14
    uth
    -0.13
     veil
    -0.13
    POSITIVE LOGITS
    928
    0.16
     numberWith
    0.15
     Willi
    0.15
     Mand
    0.15
    comed
    0.14
    oram
    0.14
    kip
    0.14
     Gear
    0.14
    olulu
    0.14
    _MAJOR
    0.14
    Act Density 0.005%

    No Known Activations